Reliable models have been urgently needed to measure the loan default risk of small businesses. Using part of the 2015-2017 PPDF online lending data as the sample, this study develops an online loan default risk identification model for small businesses with a machine learning approach. The dataset employed is from Model Whale. On the sample dataset, a maximum information value method is employed to bin features. And then the one-hot encoding technique is used to split the original features into feature variables by their numerical size, based on which we train a modified stacking heterogeneous ensemble model. Each sample point in the training set is given a weight based on its contribution to the forecasting accuracy in the 5 base classifiers in level-0 model. Specifically, k-fold cross-validation is employed, where 5 base classifiers are used to classify each sample in the train set individually. The weight assigned to each sample point depends on the times of correct identifications for this very point. The aim is to adjust adaptively the influence of these points in fitting the aforementioned model. Our work shows that, the proposed stacking model with weights achieves significantly higher accuracy in default risk identification than the conventional stacking model or other commonly used ones.
A growing number of companies are incorporating internal carbon pricing into their climate management strategies, making it one of the ways in which the private sector can combat carbon emissions and respond to the climate crisis. In this study, we used the synthetic control method in an attempt to discover whether the implementation of internal carbon pricing has an impact on the carbon reduction of typical firms at an individual level. As some of the firms cannot be properly fitted, statistical approaches were then applied to the S&P 500 constituent firms to test if there is any correlation between the emission cuts and internal carbon pricing. We also conducted a channel analysis and found that internal carbon pricing affects the amount of carbon emissions by firms mainly through two channels, namely the level of energy intensity and R&D investments. Among them, the energy intensity plays a positive mediating role between emission reduction and internal carbon pricing. As to another channel, contrary to expectations, internal carbon pricing, to some extent, suppresses the R&D investments which will promote carbon emission reduction. That is, the size of R&D investments has masking effects in the relationship between emission cuts and internal carbon pricing. Our findings contribute to researches on the carbon pricing, emission reduction and climate management efforts from the private sector, and have implications for practices.
Portfolio investment is adopted by the venture capital to diversify those risks involved in project selection, investing or operating so that the venture capitalist can expect a relatively stable income and lower financing risks. Based on the design of portfolio investment contract with unlimited funds developed by Kanniainen and Keuschnigg, and Inderst et al., this article makes a modification and presents a model given the limitation of funds available for the venture capitalist. It is demonstrated that the marginal benefit of efforts paid by the entrepreneurs exceeds the marginal cost, given the limitation of funds available, which will conduce to a high-level engagement of the entrepreneurs. Thus, by adopting the design of renegotiation contract, the venture capitalist can manage to stimulate the entrepreneurs to make efforts, which is to result in moral hazard reduction.